Prompt management
Prompt management is the systematic creation, organization, versioning, evaluation, and operational control of prompts used in AI applications.
Machine Learning Platform Engineering
Prompt management is the controlled creation, versioning, evaluation, and deployment of prompts for language-model applications.
- How it is used
- Treats LLM prompts as managed production assets rather than hardcoded application strings.
- How deep it goes
- Works through creation, labeling, runtime fetching, compilation, tracking, testing, and caching; does not specify a universal prompt-quality metric.
- Examples
- Uses a documentation assistant’s templated chat prompt, production configuration, tracked generation, and fallback boundary prompt.
- What you can do after
- Apply it via Langfuse to update, deploy, compare, and roll back prompt versions without redeploying application code.
Read how Machine Learning Platform Engineering explains prompt management →
Build AI-Enhanced Web Apps
Prompt management is the organized storage, updating, versioning, and governance of prompts used by an AI application.
- How it is used
- Keeps application prompts updateable and governed outside code while supporting version comparison in AI web applications.
- How deep it goes
- Explains storage rationale and an integration architecture, with version and test examples; does not demonstrate a database implementation.
- Examples
- Uses versioned translation templates, Vitest output checks, and a PlantUML diagram-generation architecture.
- What you can do after
- Evaluate and organize prompt variants for updates, testing, and rollback; understand where a prompt store fits in an AI application.
Read how Build AI-Enhanced Web Apps explains prompt management →
Prompt Engineering in Practice
A system for managing prompts across their production lifecycle, including collaboration, governance, and lifecycle visibility.
- How it is used
- Keeps production prompts findable, changeable, and accountable as teams and prompt libraries grow.
- How deep it goes
- Details lifecycle steps, PMS capabilities, and audit gaps; leaves deployment pipelines and telemetry backends outside scope.
- Examples
- Contrasts audit-log entries for a properly promoted prompt and a direct production edit investigated after an incident.
- What you can do after
- Practice/perform it by assessing maturity, moving prompts through a lifecycle, and using process signals to prioritize improvements.
Read how Prompt Engineering in Practice explains prompt management →
Generative AI in Action
Prompt management is the systematic design, testing, deployment, refinement, and operational maintenance of prompts for language models.
- How it is used
- Deploys prompts as an orchestration-layer capability for improving language-model responses in enterprise applications.
- How deep it goes
- Explains engineering, optimization, and PromptOps with metrics, feedback, token limits, testing, and version control, but defers fuller governance details.
- Examples
- Uses news summarization, adaptive user-intent prompts, domain-specific language, interaction analysis, A/B testing, and response-quality feedback.
- What you can do after
- Evaluate/understand prompt performance by monitoring accuracy and relevance, refining from feedback, and managing complexity, tokens, versions, and rollbacks.
Read how Generative AI in Action explains prompt management →
Related concepts
- Langfuseused by · Langfuse is an open-source observability platform for tracing, monitoring, analyzing, and evaluating applications built with large language models.
- prompt engineeringkind of · Prompt engineering is the deliberate design and refinement of instructions, context, examples, or other inputs to guide an AI model’s behavior or outputs.
- optimizationhas part · Optimization is the systematic selection or adjustment of values, actions, or system designs to improve a specified objective, often subject to constraints.
- promptopshas part · PromptOps is the operational discipline of managing prompts and prompt-based workflows through development, evaluation, deployment, monitoring, and maintenance.
- maturity journeyused by · The Maturity Journey is a framework for assessing a team's prompt-management maturity and identifying its next practical improvement step.
- language modeluses · A language model is a computational model that represents patterns in linguistic tokens to estimate sequence probabilities and predict or generate language from context.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.